We revisit a self-supervised method that segments unlabelled speech into word-like segments. We start from the two-stage duration-penalised dynamic programming method that performs zero-resource segmentation without learning an explicit lexicon. In the first acoustic unit discovery stage, we replace contrastive predictive coding features with HuBERT. After word segmentation in the second stage, we get an acoustic word embedding for each segment by averaging HuBERT features. These embeddings are clustered using K-means to get a lexicon. The result is good full-coverage segmentation with a lexicon that achieves state-of-the-art performance on the ZeroSpeech benchmarks.
Voice conversion aims to transform source speech into a different target voice. However, typical voice conversion systems do not account for rhythm, which is an important factor in the perception of speaker identity. To bridge this gap, we introduce Urhythmic-an unsupervised method for rhythm conversion that does not require parallel data or text transcriptions. Using self-supervised representations, we first divide source audio into segments approximating sonorants, obstruents, and silences. Then we model rhythm by estimating speaking rate or the duration distribution of each segment type. Finally, we match the target speaking rate or rhythm by time-stretching the speech segments. Experiments show that Urhythmic outperforms existing unsupervised methods in terms of quality and prosody. Code and checkpoints: https://github.com/bshall/urhythmic. Audio demo page: https://ubisoft-laforge.github.io/speech/urhythmic.
Any-to-any voice conversion aims to transform source speech into a target voice with just a few examples of the target speaker as a reference. Recent methods produce convincing conversions, but at the cost of increased complexity -- making results difficult to reproduce and build on. Instead, we keep it simple. We propose k-nearest neighbors voice conversion (kNN-VC): a straightforward yet effective method for any-to-any conversion. First, we extract self-supervised representations of the source and reference speech. To convert to the target speaker, we replace each frame of the source representation with its nearest neighbor in the reference. Finally, a pretrained vocoder synthesizes audio from the converted representation. Objective and subjective evaluations show that kNN-VC improves speaker similarity with similar intelligibility scores to existing methods. Code, samples, trained models: https://bshall.github.io/knn-vc
We propose a visually grounded speech model that acquires new words and their visual depictions from just a few word-image example pairs. Given a set of test images and a spoken query, we ask the model which image depicts the query word. Previous work has simplified this problem by either using an artificial setting with digit word-image pairs or by using a large number of examples per class. We propose an approach that can work on natural word-image pairs but with less examples, i.e. fewer shots. Our approach involves using the given word-image example pairs to mine new unsupervised word-image training pairs from large collections of unlabelled speech and images. Additionally, we use a word-to-image attention mechanism to determine word-image similarity. With this new model, we achieve better performance with fewer shots than any existing approach.
The goal of voice conversion is to transform source speech into a target voice, keeping the content unchanged. In this paper, we focus on self-supervised representation learning for voice conversion. Specifically, we compare discrete and soft speech units as input features. We find that discrete representations effectively remove speaker information but discard some linguistic content - leading to mispronunciations. As a solution, we propose soft speech units. To learn soft units, we predict a distribution over discrete speech units. By modeling uncertainty, soft units capture more content information, improving the intelligibility and naturalness of converted speech. Samples available at https://ubisoft-laforge.github.io/speech/soft-vc/
This paper presents Daft-Exprt, a multi-speaker acoustic model advancing the state-of-the-art on inter-speaker and inter-text prosody transfer. This improvement is achieved using FiLM conditioning layers, alongside adversarial training that encourages disentanglement between prosodic information and speaker identity. The acoustic model inherits attractive qualities from FastSpeech 2, such as fast inference and local prosody attributes prediction for finer grained control over generation. Experimental results show that Daft-Exprt significantly outperforms strong baselines on prosody transfer tasks, while yielding naturalness comparable to state-of-the-art expressive models. Moreover, results indicate that adversarial training effectively discards speaker identity information from the prosody representation, which ensures Daft-Exprt will consistently generate speech with the desired voice. We publicly release our code and provide speech samples from our experiments.
Contrastive predictive coding (CPC) aims to learn representations of speech by distinguishing future observations from a set of negative examples. Previous work has shown that linear classifiers trained on CPC features can accurately predict speaker and phone labels. However, it is unclear how the features actually capture speaker and phonetic information, and whether it is possible to normalize out the irrelevant details (depending on the downstream task). In this paper, we first show that the per-utterance mean of CPC features captures speaker information to a large extent. Concretely, we find that comparing means performs well on a speaker verification task. Next, probing experiments show that standardizing the features effectively removes speaker information. Based on this observation, we propose a speaker normalization step to improve acoustic unit discovery using K-means clustering of CPC features. Finally, we show that a language model trained on the resulting units achieves some of the best results in the ZeroSpeech2021~Challenge.
We investigate segmenting and clustering speech into low-bitrate phone-like sequences without supervision. We specifically constrain pretrained self-supervised vector-quantized (VQ) neural networks so that blocks of contiguous feature vectors are assigned to the same code, thereby giving a variable-rate segmentation of the speech into discrete units. Two segmentation methods are considered. In the first, features are greedily merged until a prespecified number of segments are reached. The second uses dynamic programming to optimize a squared error with a penalty term to encourage fewer but longer segments. We show that these VQ segmentation methods can be used without alteration across a wide range of tasks: unsupervised phone segmentation, ABX phone discrimination, same-different word discrimination, and as inputs to a symbolic word segmentation algorithm. The penalized method generally performs best. While results are only comparable to the state-of-the-art in some cases, in all tasks a reasonable competing approach is outperformed at a substantially lower bitrate.
Developments in weakly supervised and self-supervised models could enable speech technology in low-resource settings where full transcriptions are not available. We consider whether keyword localisation is possible using two forms of weak supervision where location information is not provided explicitly. In the first, only the presence or absence of a word is indicated, i.e. a bag-of-words (BoW) labelling. In the second, visual context is provided in the form of an image paired with an unlabelled utterance; a model then needs to be trained in a self-supervised fashion using the paired data. For keyword localisation, we adapt a saliency-based method typically used in the vision domain. We compare this to an existing technique that performs localisation as a part of the network architecture. While the saliency-based method is more flexible (it can be applied without architectural restrictions), we identify a critical limitation when using it for keyword localisation. Of the two forms of supervision, the visually trained model performs worse than the BoW-trained model. We show qualitatively that the visually trained model sometimes locate semantically related words, but this is not consistent. While our results show that there is some signal allowing for localisation, it also calls for other localisation methods better matched to these forms of weak supervision.
In this paper, we explore vector quantization for acoustic unit discovery. Leveraging unlabelled data, we aim to learn discrete representations of speech that separate phonetic content from speaker-specific details. We propose two neural models to tackle this challenge. Both models use vector quantization to map continuous features to a finite set of codes. The first model is a type of vector-quantized variational autoencoder (VQ-VAE). The VQ-VAE encodes speech into a discrete representation from which the audio waveform is reconstructed. Our second model combines vector quantization with contrastive predictive coding (VQ-CPC). The idea is to learn a representation of speech by predicting future acoustic units. We evaluate the models on English and Indonesian data for the ZeroSpeech 2020 challenge. In ABX phone discrimination tests, both models outperform all submissions to the 2019 and 2020 challenges, with a relative improvement of more than 30%. The discovered units also perform competitively on a downstream voice conversion task. Of the two models, VQ-CPC performs slightly better in general and is simpler and faster to train. Probing experiments show that vector quantization is an effective bottleneck, forcing the models to discard speaker information.